summarize

A command for creating a short handoff summary of the current conversation, including completed work, next steps, files, decisions, and blockers.

In plain words
What is it for?
Use it to record what was done, what remains, which files were involved, and what information or decisions are still needed.
Why use it?
It preserves the important context when work moves to another conversation, while avoiding restricted plan files.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/wbern/agent-instructions/summarize
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00481
Opus 5 $0.00004 $0.00241
Sonnet 5 $0.00002 $0.00096
Haiku 4.5 $0.00001 $0.00048

Measured 2d ago against content hash 89a07030a47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/summarize.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

Create a concise summary of the current conversation suitable for transferring context to a new conversation.

User arguments:

Summarize: $ARGUMENTS

End of user arguments

Summary Structure

Provide a summary with these sections:

What We Did

  • Key accomplishments and changes made
  • Important decisions or discoveries
  • Files created, modified, or analyzed

What We're Doing Next

  • Immediate next steps
  • Pending tasks or work in progress
  • Goals or objectives to continue

Blockers & User Input Needed

  • Any issues requiring user intervention
  • Decisions that need to be made
  • Missing information or clarifications needed

Output Format

Keep the summary concise and actionable - suitable for pasting into a new conversation to quickly restore context without needing the full conversation history.

Beads Integration

If Beads MCP is available, check for task tracking status and ask if the user wants to:

  1. Review current task status
  2. Update task states based on conversation progress
  3. Include Beads context in the summary

Use AskUserQuestion to confirm Beads integration preferences.

Testing Requirements

Change Required
Content (fragment/source) Snapshot update
Feature flag Conditional test (enabled + disabled), FLAG_OPTIONS, CLI mock
CLI option cli.test.ts mock
Generation logic Unit test

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 74 lines · 8 tokens per session scan A 89a07030a47e

Subscribe to this mod's changes

summarize is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 481 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.